AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Noise is a Good Teacher: A Noise-Driven Framework for Robust Collaborative Perception

Chengyan Huang, Zhongxiang Zhao, Ziyao Zhang, Zihao Yang, Lin Wang

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-level pose noise injection (Module A) (ablation)NoiseGT · V2X-Sim (pose noise 1.2/1.2)AP@0.7: 0.577 -> 0.638Improved
add multi-level pose noise injection (Module A) (ablation)NoiseGT · V2X-Sim (clean pose)AP@0.7: 0.838 -> 0.824Hurt
add feature denoiser (Module B) (ablation)NoiseGT · V2X-Sim (clean pose)AP@0.7: 0.838 -> 0.851Improved
add feature denoiser (Module B) alone (ablation)NoiseGT · V2X-Sim (pose noise 1.2/1.2)AP@0.7: 0.577 -> 0.577No clear effect
combine modules A and B (ablation)NoiseGT · V2X-Sim (pose noise 1.2/1.2)AP@0.7: 0.638 -> 0.661Improved
replace fixed Gaussian smoothing with learned noise-driven denoiser (ablation)NoiseGT FDM · V2X-Sim (pose noise 1.2/1.2)AP@0.7: 0.613 -> 0.661Improved
add noise injection and denoise loss over architecture-only refinement (ablation)NoiseGT FDM · V2X-Sim (pose noise 1.2/1.2)AP@0.7: 0.654 -> 0.661Improved
add explicit denoising over noise augmentation only (ablation)NoiseGT · V2X-Sim (pose noise 1.2/1.2)AP@0.7: 0.612 -> 0.661Improved
add NoiseGT multi-level noise injection to RoCo solverRoCo · V2X-Sim (pose noise 1.2/1.2)AP@0.5: 0.703 -> 0.733Improved
swap PointPillars for SECOND backbone with NoiseGT vs CoAlignNoiseGT · V2X-Sim SECOND (pose noise 1.2/1.2)AP@0.5: 0.667 -> 0.720Improved
swap PointPillars for VoxelNet backbone with NoiseGT vs CoAlignNoiseGT · V2X-Sim VoxelNet (pose noise 1.2/1.2)AP@0.5: 0.683 -> 0.741Improved
use NoiseGT instead of CoDiff at matched one diffusion stepNoiseGT · DAIR-V2X (pose noise 1.2/1.2)AP@0.5: 0.652 -> 0.691Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy